Cargando…
3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts
Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than ot...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7915739/ https://www.ncbi.nlm.nih.gov/pubmed/33557360 http://dx.doi.org/10.3390/s21041078 |
_version_ | 1783657316305862656 |
---|---|
author | Merino, Ibon Azpiazu, Jon Remazeilles, Anthony Sierra, Basilio |
author_facet | Merino, Ibon Azpiazu, Jon Remazeilles, Anthony Sierra, Basilio |
author_sort | Merino, Ibon |
collection | PubMed |
description | Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than other 3D deep learning methods, and even worse than their 2D version. In this paper, we propose to improve 3D deep learning results by transferring the pretrained weights learned in 2D networks to their corresponding 3D version. Using an industrial object recognition context, we have analyzed different combinations of 3D convolutional networks (VGG16, ResNet, Inception ResNet, and EfficientNet), comparing the recognition accuracy. The highest accuracy is obtained with EfficientNetB0 using extrusion with an accuracy of 0.9217, which gives comparable results to state-of-the art methods. We also observed that the transfer approach enabled to improve the accuracy of the Inception ResNet 3D version up to 18% with respect to the score of the 3D approach alone. |
format | Online Article Text |
id | pubmed-7915739 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-79157392021-03-01 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts Merino, Ibon Azpiazu, Jon Remazeilles, Anthony Sierra, Basilio Sensors (Basel) Article Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than other 3D deep learning methods, and even worse than their 2D version. In this paper, we propose to improve 3D deep learning results by transferring the pretrained weights learned in 2D networks to their corresponding 3D version. Using an industrial object recognition context, we have analyzed different combinations of 3D convolutional networks (VGG16, ResNet, Inception ResNet, and EfficientNet), comparing the recognition accuracy. The highest accuracy is obtained with EfficientNetB0 using extrusion with an accuracy of 0.9217, which gives comparable results to state-of-the art methods. We also observed that the transfer approach enabled to improve the accuracy of the Inception ResNet 3D version up to 18% with respect to the score of the 3D approach alone. MDPI 2021-02-04 /pmc/articles/PMC7915739/ /pubmed/33557360 http://dx.doi.org/10.3390/s21041078 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Merino, Ibon Azpiazu, Jon Remazeilles, Anthony Sierra, Basilio 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts |
title | 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts |
title_full | 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts |
title_fullStr | 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts |
title_full_unstemmed | 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts |
title_short | 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts |
title_sort | 3d convolutional neural networks initialized from pretrained 2d convolutional neural networks for classification of industrial parts |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7915739/ https://www.ncbi.nlm.nih.gov/pubmed/33557360 http://dx.doi.org/10.3390/s21041078 |
work_keys_str_mv | AT merinoibon 3dconvolutionalneuralnetworksinitializedfrompretrained2dconvolutionalneuralnetworksforclassificationofindustrialparts AT azpiazujon 3dconvolutionalneuralnetworksinitializedfrompretrained2dconvolutionalneuralnetworksforclassificationofindustrialparts AT remazeillesanthony 3dconvolutionalneuralnetworksinitializedfrompretrained2dconvolutionalneuralnetworksforclassificationofindustrialparts AT sierrabasilio 3dconvolutionalneuralnetworksinitializedfrompretrained2dconvolutionalneuralnetworksforclassificationofindustrialparts |